© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111644
    Prev
    Next
    INDEX
    Explanations

    as it turns out

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects occurrences of the phrase “turns out.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    甞
    -1.55
     conne
    -1.52
    leggio
    -1.51
    cyclic
    -1.47
     impor
    -1.44
    BeNil
    -1.41
     ∼
    -1.37
     incar
    -1.35
    tifies
    -1.34
     SETS
    -1.34
    POSITIVE LOGITS
     However
    1.55
     From
    1.53
     veritable
    1.39
     Niemand
    1.35
     преиму
    1.35
     from
    1.34
    konfirmasi
    1.33
     najczęściej
    1.33
     most
    1.33
     This
    1.33
    Activations Density 0.012%

    No Known Activations